Control method and equipment for pollutant concentration of clean room, medium and product

Abstract

The invention provides a clean room pollutant concentration control method, equipment, a medium and a product, and relates to the technical field of clean room ventilation control. The method comprises the following steps: acquiring the real-time gaseous molecular pollutant AMC concentration of each region in a clean room according to the space region division result of the clean room; when the real-time AMC concentration of the target area is larger than or equal to a concentration threshold value, the target area serves as the center, and the wind speed correction value of the FFU of each area is adjusted according to the distance between the other areas and the target area; wherein the closer the distance to the target area is, the larger the corresponding wind speed correction value is; when the AMC concentration of the target area is smaller than a concentration threshold value, the current AMC concentration value of each area is obtained, and an FFU wind speed optimal solution is determined according to the current AMC concentration value of each area, clean room FFU layout information and a particle swarm optimization algorithm PSO; and adjusting the wind speed of each FFU according to the optimal solution of the wind speed of the FFU. According to the invention, global monitoring, dynamic optimization and accurate regulation and control of pollution concentration can be realized.

Description

Technical Field

[0001] This invention relates to the field of cleanroom ventilation control technology, and in particular to a method, equipment, medium and product for controlling the concentration of pollutants in cleanrooms. Background Technology

[0002] Cleanrooms are indispensable infrastructure in high-tech fields such as semiconductor manufacturing, biomedicine, and aerospace, and their environmental quality directly affects product yield and performance stability. With continuous technological advancements, the requirements for controlling airborne molecular contaminants (AMCs) in cleanrooms are becoming increasingly stringent. AMCs include various chemical molecules (such as acidic gases, alkaline gases, and volatile organic compounds), and even trace amounts can lead to corrosion, performance degradation, or even failure of sensitive components. Against this backdrop, efficient and precise AMC monitoring and control technologies have become one of the core research topics in the cleanroom industry.

[0003] Currently, the monitoring and control of air pollution concentration (AMC) in cleanrooms mainly relies on the following technical means: First, monitoring AMC concentration through fixed-location gas sensors and notifying personnel via early warning for manual adjustment; second, adjusting airflow velocity in conjunction with the air supply system and fan filter units (FFUs) to dilute contaminant concentration; and third, reducing AMC concentration through high-efficiency filters or chemical adsorption equipment under specific conditions. These methods can alleviate pollution problems to some extent, but their implementation typically relies on static rules or manual intervention, lacking dynamic adjustment capabilities. Furthermore, many systems employ wind speed adjustment logic based on preset parameters, failing to fully utilize real-time data and intelligent optimization methods for precise control.

[0004] While traditional methods can meet some application needs, their limitations are becoming increasingly apparent when faced with frequent changes in contaminant sources within cleanrooms, the dynamic complexity of contaminant distribution, and increasingly stringent requirements for gas quality. First, sensors have limited monitoring range and slow response times, making it impossible to generate real-time contaminant concentration maps. Second, manual or rule-based wind speed adjustments struggle to respond quickly and accurately to sudden contamination events, potentially leading to increased energy consumption or contaminant spread. Finally, the lack of global optimization and dynamic feedback mechanisms prevents the balancing of airflow throughout the cleanroom after local adjustments, which could result in secondary contamination in other areas.

[0005] Therefore, there is an urgent need for an AMC monitoring and control system based on real-time data and intelligent algorithms to achieve global monitoring, dynamic optimization and precise control of pollution concentration, thereby making up for the shortcomings of existing technologies. Summary of the Invention

[0006] This invention provides a method, equipment, medium, and product for controlling the concentration of contaminants in cleanrooms, in order to solve the problems of global monitoring, dynamic optimization, and precise control of contaminant concentration.

[0007] In a first aspect, embodiments of the present invention provide a method for controlling the concentration of contaminants in a cleanroom, characterized in that it includes: Based on the cleanroom space zoning results, the real-time AMC concentration in each area of ​​the cleanroom is obtained; When the real-time AMC concentration in the target area is greater than or equal to the concentration threshold, the wind speed correction value of each FFU in the other areas is adjusted according to the distance between the target area and the target area, with the target area as the center; wherein, the closer the distance to the target area, the larger the corresponding wind speed correction value. When the AMC concentration in the target area is less than the concentration threshold, the current AMC concentration value of each area is obtained, and the optimal solution for FFU wind speed is determined based on the current AMC concentration value of each area, the cleanroom FFU layout information, and the Particle Swarm Optimization (PSO) algorithm. Adjust the wind speed of each FFU according to the optimal solution of FFU wind speed.

[0008] In one possible implementation, determining the optimal FFU velocity based on the current AMC concentration value of each area, the cleanroom FFU layout information, and the PSO includes: Determine the number of FFUs based on the cleanroom FFU layout information; Initialize the particle swarm size, particle position, and particle velocity using the number of FFUs, the current wind speed of each FFU, and wind speeds within a set wind speed range. In each iteration, the fitness function value of the particle corresponding to each FFU is calculated, and the individual optimal position is updated according to the wind speed corresponding to the optimal fitness of each FFU. The global optimal position is updated according to the wind speed corresponding to the optimal fitness of all FFUs. Based on the individual optimal position and the global optimal position, the velocity and position of the particles corresponding to each FFU are updated. When the convergence condition is met, the corresponding global optimal solution is used as the optimal solution for the FFU wind speed.

[0009] In one possible implementation, the convergence condition includes: In multiple consecutive iterations, the change in the fitness function value corresponding to the global optimal position is less than a set threshold, or the number of iterations reaches the preset maximum number.

[0010] In one possible implementation, obtaining the real-time AMC concentration in each area of ​​the cleanroom includes: AMC concentration monitoring data is collected from all sensors distributed throughout the cleanroom space at a set period; wherein, the AMC concentration monitoring data includes sensor number and AMC concentration detection value; The coordinates of the sensor are determined based on the sensor number, and a data matrix is ​​constructed based on the sensor coordinates and the corresponding AMC concentration detection value. A concentration map is drawn based on the data matrix, and the average AMC concentration of all grid points in each region is determined as the AMC concentration of each region based on the concentration map.

[0011] In one possible implementation, before determining the sensor's coordinates based on the sensor number, the method further includes: The AMC concentration detection values ​​of each sensor are preprocessed; the preprocessing includes outlier detection, missing value imputation and noise reduction smoothing.

[0012] In one possible implementation, drawing the concentration map based on the data matrix includes: The target grid points with missing AMC concentration values ​​are determined by comparing the coordinates of each grid point with those of the sensor. Calculate the AMC concentration value of the target grid point based on the data matrix and interpolation algorithm; A concentration map is drawn based on the AMC concentration values ​​and grid coordinates of each grid point.

[0013] In one possible implementation, calculating the AMC concentration value of the target grid point based on the data matrix and the interpolation algorithm includes: The AMC concentration value of the target grid point is determined using the inverse distance weighting method, as shown in the following formula:

[0014] in, For the first AMC concentration values ​​from each sensor; For grid points To the sensor Euclidean distance: ; This is the distance-weighted index.

[0015] Secondly, embodiments of the present invention provide a device for controlling the concentration of contaminants in a cleanroom, comprising: The acquisition module is used to obtain the real-time AMC concentration in each area of ​​the cleanroom based on the cleanroom space area division results; The wind speed correction module is used to adjust the wind speed correction value of each FFU in a target area based on the distance between the target area and the target area when the real-time AMC concentration in the target area is greater than or equal to the concentration threshold; wherein, the closer the distance to the target area, the larger the corresponding wind speed correction value. The wind speed optimization module is used to obtain the current AMC concentration value of each area when the AMC concentration in the target area is less than the concentration threshold, and determine the optimal solution for FFU wind speed based on the current AMC concentration value of each area, cleanroom FFU layout information and PSO. The adjustment module is used to adjust the wind speed of each FFU according to the optimal solution of the FFU wind speed.

[0016] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0017] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0018] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0019] In this embodiment of the invention, the cleanroom contaminant concentration control method monitors the AMC concentration in each area in real time. When the concentration in a target area exceeds the limit, the FFU wind speed correction value is adjusted based on the distance from that area, with the correction value increasing as the distance increases. This method can specifically strengthen airflow control near the contaminant source and quickly suppress contaminant diffusion. Once the concentration drops below the threshold, the optimal wind speed is determined by combining the current concentration, FFU layout, and PSO algorithm. This ensures the stability of the overall cleanroom concentration and achieves global wind speed optimization through intelligent algorithms, thus ensuring both rapid response to contamination risks and high system efficiency. Attached Figure Description

[0020] Figure 1 This is an application scenario diagram of the cleanroom contaminant concentration control method provided in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the implementation of the cleanroom contaminant concentration control method provided in this embodiment of the invention. Figure 3This is a schematic diagram of the structure of the cleanroom contaminant concentration control device provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0022] Figure 1 This diagram illustrates an application scenario of the cleanroom contaminant concentration control method provided in this embodiment of the invention. Figure 1 As shown, multiple concentration sensors and FFUs are distributed within the cleanroom. A control terminal is used to remotely collect data from the concentration sensors and FFUs. By combining the concentration detection results with the FFU airflow, the control terminal can promptly adjust the FFU airflow based on changes in the cleanroom's contaminant concentration, thereby meeting the multi-faceted requirements of global monitoring, dynamic optimization, and precise control of contaminant concentration. Unless otherwise specified in the embodiments of this application, the sensor refers to the concentration sensor installed in the cleanroom to detect AMC concentration.

[0023] During the concentration sensor layout process, ensure that the sensors can cover all critical areas of the cleanroom, including potential sources of contamination, areas with weak airflow, and the distribution center of FFUs.

[0024] Assuming the cleanroom area is Divide it into There are 3 cells, each with the same area. The center point of the sensor is defined as... At least one sensor should be placed in each cell. In areas where contaminants diffuse rapidly (such as cleanroom entrances and equipment operating areas), the sensor density should be appropriately increased. If the entire cleanroom is divided into high-risk and low-risk areas, the sensor spacing in high-risk areas should be adjusted accordingly. Smaller spacing between low-risk areas It can be increased appropriately.

[0025] Calculate the total number of sensors based on the sensor spacing. :

[0026] in, The spacing between the sensors, It depends on the cleanliness level of the cleanroom and the characteristics of contaminant diffusion.

[0027] During the concentration acquisition process, each sensor periodically acquires the AMC concentration value, recorded as follows: The unit is ppb. The data acquisition frequency is set to per second or higher, depending on the rate of contaminant diffusion and control requirements within the cleanroom. Sensor data is transmitted to the central control system via wireless transmission (such as WiFi, ZigBee) or wired transmission (such as Ethernet).

[0028] The control terminal uses sensor numbers and its coordinates For identification purposes, save as a real-time data matrix:

[0029] To visualize concentration distribution, the concentration matrix can be displayed as a heatmap for rapid identification of pollution sources and abnormal areas. Color intensity indicates the level of AMC concentration. For example: green: low concentration, good air quality; yellow: concentration near the threshold, requiring attention; red: concentration exceeds the standard, immediate adjustment is needed. The concentration map can be dynamically updated based on the constructed real-time data matrix.

[0030] To improve the real-time performance of pollutant concentration monitoring, the concentration map is updated at fixed time intervals (e.g., 1 second) based on the latest sensor data. The updated concentration map will then be used for subsequent FFU (Fan Filter Unit) wind speed adjustments.

[0031] During FFU (Fan Filter Unit) layout, ensure that FFUs are evenly distributed within the cleanroom, covering all areas. Achieve uniform airflow within the cleanroom, avoiding dead zones and overflow zones. Each FFU is responsible for airflow and purification within its coverage area. Assume the cleanroom is divided into a grid, with one FFU at each grid point. Determine the FFU installation direction and density based on the cleanroom's airflow design requirements (e.g., unidirectional or non-unidirectional flow).

[0032] Furthermore, in order to optimize the FFU layout, the FFU density needs to be increased in high cleanliness level areas (such as ISO 5 level), while the density can be appropriately reduced in low cleanliness level areas.

[0033] Assuming the area of ​​the cleanroom is Divide it into The grid is defined. The center point of each grid cell represents the location of an FFU, with coordinates expressed as follows: ,in Each FFU is assigned a unique number. And record its location. .

[0034] In actual implementation, the area each FFU is responsible for is defined as its own grid and its surrounding area, referred to as the "FFU influence area". Defined as A certain range centered on the grid, typically the grid size. Ensure that all grid points are covered by at least one FFU.

[0035] To ensure that all grid points are covered by at least one FFU, verification is performed according to the following formula: For each grid point Calculate the distance between it and the nearest FFU. :

[0036] If the distance from any grid point to the FFU exceeds the specified maximum range If so, the number of FFUs needs to be increased or the layout adjusted. The specified maximum range... The distance between FFUs should be set according to the cleanliness level requirements of the cleanroom to avoid insufficient cleanliness capacity caused by excessive distance between them.

[0037] The cleanroom contaminant concentration control method provided in this application is based on the above. To make the specific process of the cleanroom contaminant concentration control method clearer, the method embodiment will be described in detail below with reference to the accompanying drawings.

[0038] See Figure 2 The document illustrates a flowchart of the cleanroom contaminant concentration control method provided in this embodiment of the invention, comprising the following steps: S201, based on the cleanroom space zoning results, obtain the real-time AMC concentration in each area of ​​the cleanroom.

[0039] The execution entity in the various embodiments of this application can be a server, processor, microprocessor, or other device with data processing capabilities. In actual implementation, the specific implementation method of the execution entity can be selected according to actual needs. This embodiment does not impose any particular limitation on this; any device with data processing capabilities is acceptable. For ease of understanding of the embodiments of this application, [the following is used as an example]. Figure 1 The control terminal shown is used to illustrate the execution entity.

[0040] As described above, the entire cleanroom is divided into high-risk and low-risk areas. In other embodiments, the cleanroom space can optionally be divided into zones based on the functionality of different areas. This is to comprehensively understand the distribution of contaminants within the cleanroom and obtain the real-time AMC concentration in each area.

[0041] S202, when the real-time AMC concentration in the target area is greater than or equal to the concentration threshold, the wind speed correction value of each FFU in the other areas is adjusted according to the distance between the target area and the target area, with the target area as the center; the closer the distance to the target area, the larger the corresponding wind speed correction value.

[0042] Among them, if the concentration value of a certain area Exceeding the preset threshold If the target area is identified as a pollution source, the system triggers a local optimization response, adjusting the FFU wind speeds in the target area and surrounding areas. Triggering condition formula:

[0043] The wind speed correction values ​​of FFUs in each area are adjusted based on the distance between the remaining areas and the target area. This aims to quickly respond to a sudden increase in AMC concentration in a certain area of ​​the cleanroom, prioritizing the adjustment of FFU wind speeds in that area and its adjacent areas to rapidly reduce contamination concentration and prevent contamination spread. This ensures that local contamination events are controlled within a short period of time, while also laying the foundation for subsequent global optimization.

[0044] In different embodiments, the range of FFUs adjusted when adjusting the wind speed correction value of each region's FFU is different.

[0045] In one possible implementation, if the area of ​​the cleanroom or the number of FFUs in the cleanroom is small, the airflow velocity of the FFUs in all areas of the cleanroom can be adjusted.

[0046] In other possible implementations, when the cleanroom space is large, the number of FFUs is large, or the AMC concentration increase is small, the airflow speed of the FFUs within a set distance around the target area can be adjusted to avoid concentration fluctuations in other distant areas.

[0047] For example: the location of the pollution source, i.e., the target area where the real-time AMC concentration is greater than or equal to the concentration threshold, is... The corresponding AMC concentration is The radius extends outwards from the pollution source to adjacent areas. All FFU points within the range are the adjustment targets.

[0048] FFU set in the neighboring area:

[0049] in, The radius of extension outside the adjacent area; Target area To FFU Euclidean distance:

[0050] Prioritize reducing the wind speed of FFUs in the target area to minimize their diffusion effect. For FFUs in adjacent areas, the wind speed of FFUs closer to the pollution source is increased more, while the wind speed of FFUs farther away is increased less, with weights decreasing according to distance. For the target area... The FFU reduces its wind speed. To reduce the spread of pollutants. The wind speed adjustment formula is:

[0051] in, The wind speed of the FFU at the pollution source; This represents the minimum wind speed of the FFU. This represents the maximum value of the FFU wind speed; This represents the maximum possible value of AMC concentration. This is a preset threshold.

[0052] For FFUs in the vicinity, wind speed is increased according to a distance-weighted decreasing principle. The closer the distance, the greater the increase in wind speed. The wind speed adjustment formula is:

[0053] in, The wind speed of the nearby FFU; The concentration value for the area to which the neighboring FFU is responsible.

[0054] In the specific implementation process, when adjusting the wind speed correction value of each region's FFU based on the distance between the other regions and the target region, a distance weighting factor is determined based on the distance between the other regions and the target region, and the wind speed correction value of each region's FFU is adjusted based on the distance weighting factor.

[0055] Specifically, based on the aforementioned wind speed adjustment formula, the wind speed of the adjacent FFU is further multiplied by a distance weighting factor. This causes FFUs closer to the pollution source to experience increased wind speed:

[0056] The comprehensive adjustment formula is as follows:

[0057] In this implementation, adjusting the wind speed of each FFU in each area according to the distance weighting factor can ensure that pollutants diffuse stably under the guidance of the wind speed of each FFU.

[0058] In other possible implementations, to improve the wind speed adjustment effect, a pre-set wind speed correction value can be determined based on the distance ranking results between the remaining areas and the target area, and the FFU wind speed can be adjusted according to the set wind speed correction value.

[0059] S203: When the AMC concentration in the target area is less than the concentration threshold, obtain the current AMC concentration value of each area, and determine the optimal FFU wind speed based on the current AMC concentration value of each area, the cleanroom FFU layout information, and the PSO.

[0060] The system monitors the concentration changes at the pollution source and its adjacent areas in real time, and the adjusted FFU wind speed takes effect immediately. The concentration distribution is recalculated and the concentration map is updated after each adjustment of the FFU wind speed.

[0061] The foregoing embodiments illustrate that the range of FFUs adjusted varies when adjusting the wind speed correction values ​​for each area's FFUs in different embodiments. Therefore, after local optimization, global optimization calculates the optimal wind speed distribution of FFUs throughout the cleanroom. This ensures that the AMC concentration in all areas of the cleanroom remains within a safe range, achieving precise control of overall pollutants. After local optimization, the local concentration may decrease, but local adjustments may disturb the airflow distribution in other areas. Therefore, after local optimization, global optimization reassesses the concentration distribution throughout the cleanroom and balances the concentration fluctuations caused by local adjustments through FFU wind speed allocation. Global optimization wind speed distribution. It will cover the results of local optimization adjustments, and balance these disturbances through overall calculation to ensure that the entire cleanroom is restored to its optimal state.

[0062] After global optimization, the system continues to monitor concentration distribution. The system monitors changes in cleanroom performance. If a new contamination event is detected, local optimization is triggered again, and a new round of global optimization begins after the local optimization is completed. Even without local contamination events, regular optimization of the cleanroom ensures overall operational efficiency and effective contamination control.

[0063] PSO is a biomimetic optimization algorithm that searches for the optimal solution to a problem by simulating the cooperative behavior of a particle swarm. In FFU wind speed optimization, each particle represents an FFU wind speed allocation scheme. The algorithm gradually approaches the optimal wind speed distribution by updating the velocity and position of the particles, achieving rapid response to pollution risks while maintaining high system efficiency.

[0064] S204, adjust the wind speed of each FFU according to the optimal solution of FFU wind speed.

[0065] After the control terminal determines the optimal FFU wind speed, it distributes the corresponding FFU wind speed according to the number of each FFU to achieve synchronous adjustment.

[0066] In this embodiment, the cleanroom contaminant concentration control method monitors the AMC concentration in each area in real time. When the concentration in a target area exceeds the limit, the FFU wind speed correction value is adjusted based on the distance from that area, with a larger correction value for closer areas. This method can specifically strengthen airflow control near the contaminant source and quickly suppress contaminant diffusion. Once the concentration drops below the threshold, the optimal wind speed is determined by combining the current concentration, FFU layout, and PSO algorithm. This ensures the stability of the overall cleanroom concentration and achieves global wind speed optimization through intelligent algorithms, thus ensuring both rapid response to contamination risks and high system efficiency.

[0067] In one possible implementation, the optimal FFU velocity is determined based on the current AMC concentration value of each area, the cleanroom FFU layout information, and the PSO, including: Determine the number of FFUs based on the cleanroom FFU layout information; Initialize the particle swarm size, particle position, and particle velocity using the number of FFUs, the current wind speed of each FFU, and wind speeds within a set wind speed range. In each iteration, the fitness function value of the particle corresponding to each FFU is calculated, and the individual optimal position is updated according to the wind speed corresponding to the optimal fitness of each FFU. The global optimal position is updated according to the wind speed corresponding to the optimal fitness of all FFUs. Based on the individual optimal position and the global optimal position, the velocity and position of the particles corresponding to each FFU are updated. When the convergence condition is met, the corresponding global optimal solution is used as the optimal solution for the FFU wind speed.

[0068] In actual implementation, each Corresponding to its area of ​​responsibility The AMC concentration value is the concentration of all grid points covering the region. Average value:

[0069] in, Indicates the area The number of grid points within.

[0070] Construct a mapping matrix between FFU and regional concentration. :

[0071] Each of them This indicates the concentration value of the area covered by the corresponding FFU.

[0072] FFU layout information, including: FFU number ,coordinate and each FFU's responsible area concentration value , represented as:

[0073] Each time the concentration map is updated, the concentration value for each FFU region is recalculated. And update the concentration distribution matrix of FFU. This provides support for subsequent FFU wind speed adjustment.

[0074] In the specific implementation process, the number of FFUs is determined based on the FFU layout information.

[0075] The fitness function is used to evaluate the effectiveness of wind speed distribution schemes and is defined as the deviation between the pollutant concentration and the target concentration. Fitness function formula:

[0076] in, This represents the wind speed distribution across all FFUs; The concentration value is calculated based on the current wind speed distribution; The target concentration value (usually the set ideal concentration range in the clean room).

[0077] Adapting to FFU control and defining particle characteristics: Position: The particle's current position This indicates the wind speed distribution of the FFU.

[0078] Velocity: the speed of a particle This determines the direction and magnitude of the particle's next wind speed adjustment.

[0079] Before determining the optimal FFU wind speed based on PSO, the particle swarm size is first initialized. The position and velocity of the particle: The initial wind speed (i.e., the particle's position) is allocated as follows:

[0080] Its value range is limited to the minimum and maximum wind speeds allowed by the FFU equipment.

[0081] The initial velocity (i.e., the particle's velocity) is:

[0082] in, Indicates the interval The system generates random numbers internally. The initial velocity is randomly set within a preset reasonable range to ensure diversity in the optimization process.

[0083] Calculate the fitness value for each particle. And update the following two items: Individual optimal position Recording particles The historically optimal wind speed allocation, i.e. the wind speed scheme with the best fitness since each FFU has been iterated. Global optimal position Record the current optimal wind speed allocation in the entire particle swarm, that is, the wind speed scheme with the best fitness among all FFUs.

[0084] The velocity of each particle is updated according to the following formula:

[0085] in, Inertial weights control the degree to which particles depend on their historical velocities. , These are learning factors, which control the particle's ability to learn from its own optimal solution and the global optimal solution, respectively. This represents the globally optimal position in the j-th iteration. For the j-th iteration particle The optimal position of an individual.

[0086] Update the position of each particle according to the following formula:

[0087] in, for The time corresponds to the position of particle j; for The time corresponds to the position of particle j; for The particle velocity at that moment.

[0088] The iteration terminates when the convergence condition is met, and the wind speed allocation scheme corresponding to the globally optimal location is taken as the target wind speed (i.e., the globally optimized value) for each region's FFUs. Globally optimal FFU wind speed allocation: .

[0089] In practice, this scheme can be used as a wind speed benchmark during daily stable operation, and can also be used as a target value to restore the FFU wind speed in the pollution source area and adjacent areas after the local optimization response is completed, so as to achieve a balance between concentration control and energy consumption optimization in the space.

[0090] In this embodiment, the method initializes particle swarm parameters based on the number of FFUs, dynamically updates individual and global optimal positions during the iteration process, and adjusts particle velocity and position accordingly. Finally, the global optimal solution at convergence is used as the optimal wind speed solution. This ensures that the optimization process of the PSO algorithm is closely integrated with the actual layout and operating parameters of the cleanroom FFUs, ensuring that the found optimal wind speed solution can adapt to the specific environment of the cleanroom, improving the practicality and reliability of the optimal solution, and thus enhancing the accuracy of concentration control.

[0091] In different embodiments, the convergence conditions vary depending on the control requirements.

[0092] In one possible implementation, the convergence condition includes: in multiple consecutive iterations, the change in the fitness function value corresponding to the global optimal position is less than a set threshold.

[0093] In actual implementation, the change in fitness value is less than the threshold. Represented as:

[0094] in, This is the latest fitness function value; This is the previous fitness function value; To set a threshold.

[0095] In this embodiment, the convergence condition is set as the change in the global optimal fitness over multiple consecutive iterations being less than a threshold. A change in the global optimal fitness less than the threshold indicates that the optimization has stabilized, and further iterations are unlikely to significantly improve the solution's performance. Therefore, stopping iteration when the change in the global optimal fitness is less than the threshold avoids the algorithm from getting stuck in meaningless loop iterations and ensures timely termination when the optimization effect stabilizes, thus saving computational resources.

[0096] In another possible implementation, the convergence condition includes: the number of iterations reaches a preset maximum number.

[0097] In this embodiment, the convergence condition is set to reach the maximum number of iterations. By limiting the maximum number of iterations, the algorithm is ensured to output results within an acceptable time, thus balancing optimization accuracy and efficiency.

[0098] In other possible implementations, the convergence conditions include: In multiple consecutive iterations, the change in the fitness function value corresponding to the global optimal position is less than a set threshold, or the number of iterations reaches the preset maximum number.

[0099] In this embodiment, the convergence condition is set to the global optimal fitness change being less than a threshold or reaching the maximum number of iterations in multiple consecutive iterations. This avoids the algorithm from getting stuck in meaningless loop iterations and ensures that it terminates in time when the optimization effect tends to stabilize to save computing resources. At the same time, the limitation of the maximum number of iterations ensures that the algorithm outputs results within an acceptable time. This balances the optimization accuracy and efficiency, making the PSO algorithm more feasible in practical applications.

[0100] In one possible implementation, the real-time AMC concentration in each area of ​​the cleanroom is obtained, including: AMC concentration monitoring data is collected from all sensors distributed throughout the cleanroom space at a set periodic rate; the AMC concentration monitoring data includes the sensor number and the AMC concentration detection value. The coordinates of the sensor are determined based on the sensor number, and a data matrix is ​​constructed based on the sensor coordinates and the corresponding AMC concentration detection value. A concentration map is drawn based on the data matrix, and the average AMC concentration of all grid points in each region is determined based on the concentration map as the AMC concentration of each region.

[0101] The real-time AMC concentration in each area of ​​the cleanroom is obtained based on the concentration spectrum described in the aforementioned embodiments. In practice, to improve the accuracy of area concentration detection, each area covers multiple grid points. Therefore, when determining the AMC concentration in each area, the average AMC concentration of all grid points within that area is used as the AMC concentration for that area, avoiding the impact of excessively high or low concentration values ​​from a single grid point on the overall accuracy of the area's AMC concentration.

[0102] In this embodiment, sensor data is collected periodically, and a data matrix is ​​constructed by combining sensor coordinates to create a concentration map. The average concentration of grid points within a region is then used as the concentration for that region, achieving refined perception of AMC concentrations in various areas of the cleanroom. This spatially distributed concentration acquisition method more accurately reflects the pollution status of different areas, providing a precise basis for subsequent wind speed adjustments and avoiding control errors caused by single-point data deviations.

[0103] In one possible implementation, before determining the sensor's coordinates based on the sensor number, the following steps are also included: The AMC concentration detection values ​​of each sensor are preprocessed; the preprocessing includes outlier detection, missing value imputation and noise reduction smoothing.

[0104] In actual implementation, the collected concentration values The system performs detection, and if the concentration value exceeds the sensor's design range (e.g., below zero or above the device's upper limit), it is marked as abnormal data. If some sensor data is missing, interpolation methods (such as linear interpolation or higher-order interpolation) are used to fill in the missing values.

[0105] During the noise reduction and smoothing process, the collected concentration values ​​are... To reduce the impact of short-term fluctuations, a moving average or Kalman filter can be applied. The formula is as follows:

[0106] in, To adjust the sliding window size; It is the index of a data point within the sliding window.

[0107] In this embodiment, preprocessing of the sensor detection values, including outlier detection, missing value imputation, and noise reduction and smoothing, effectively eliminates invalid data, supplements incomplete information, and reduces noise interference, making the constructed data matrix closer to the actual concentration distribution. Drawing concentration maps and calculating regional concentrations based on the purified data reduces the impact of data errors on concentration judgment, improves the reliability of concentration monitoring, and lays the foundation for the accurate implementation of subsequent control measures.

[0108] In one possible implementation, a concentration map is drawn based on the data matrix, including: The target grid points with missing AMC concentration values ​​are determined by comparing the coordinates of each grid point with those of the sensor. The AMC concentration values ​​of the target grid points are calculated based on the data matrix and interpolation algorithm; A concentration map is drawn based on the AMC concentration values ​​and grid coordinates of each grid point.

[0109] based on Figure 1 As indicated in the scenario diagram, the sensor density should be appropriately increased in areas where pollutants diffuse rapidly (such as cleanroom entrances and equipment operating locations). Therefore, when constructing the concentration map, some grid points in areas with low sensor density may have fewer AMC concentration values. Thus, it is necessary to supplement the missing AMC concentration values ​​for these grid points based on the density of surrounding sensors.

[0110] Specifically, the sensors around the target grid point with missing AMC concentration values ​​are determined based on the data matrix and interpolation algorithm. The concentration change trend is analyzed by combining the concentration values ​​monitored by the surrounding sensors to obtain the AMC concentration value at the target grid point.

[0111] In this embodiment, by identifying target grid points with missing concentrations and calculating their concentrations using an interpolation algorithm, a complete concentration map is drawn, thus solving the problem of spatial data gaps caused by the discrete distribution of sensors. The application of the interpolation algorithm enables the concentration map to completely cover all areas of the cleanroom, clearly presenting the spatial trend of concentration changes, helping the system to more comprehensively grasp the distribution of contaminants, thereby making subsequent area division and wind speed adjustment more targeted.

[0112] In one possible implementation, the AMC concentration values ​​of the target grid points are calculated based on the data matrix and an interpolation algorithm, including: The AMC concentration value of the target grid point is determined using the inverse distance weighting method, as shown in the following formula:

[0113] in, For the first AMC concentration values ​​from each sensor; For grid points To the sensor Euclidean distance: ; This is the distance weighting index, which is usually set to 2.

[0114] In this embodiment, the inverse distance weighting method is used to calculate the AMC concentration value of the target grid point. By assigning greater weight to sensor data closer to the target grid point, the interpolation result more closely matches the actual spatial distribution of concentration. This method fully considers the impact of spatial correlation on concentration, avoids excessive interference from distant sensor data on the concentration of nearby grid points, improves the accuracy of target grid point concentration calculation, and thus enhances the accuracy and reference value of the concentration map.

[0115] Other possible implementations include calculating the AMC concentration values ​​of the target grid points based on the data matrix and interpolation algorithm, including: Determine the number of sensors around the target grid point where the AMC concentration value is missing; The average concentration values ​​corresponding to a set number of sensors are calculated as the AMC concentration value of the target grid point, denoted as . .

[0116] In the specific implementation process, after calculating the AMC concentration value of the target grid points, a two-dimensional matrix is ​​constructed based on the AMC concentration value of each grid point to generate a concentration map:

[0117] Each element This represents the concentration value of the corresponding grid point in the matrix.

[0118] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0119] The above embodiments mainly introduce the FFU (Fan Filter Unit) airflow adjustment scheme when the real-time AMC (Active Concentration of Cleanroom Components) concentration in the target area is greater than or equal to the concentration threshold, in order to control the concentration of contaminants in the cleanroom. In specific implementation, dynamic feedback and adjustment of the contaminant concentration in the cleanroom are required to achieve real-time updates of concentration data and dynamic adjustment of FFU airflow, ensuring that the FFU airflow adjustment scheme can adapt to real-time changes in the contaminant concentration in the cleanroom. Dynamically adjusting the FFU airflow distribution in the cleanroom allows for timely response to sudden contamination events, while balancing the adjustment results of local and global optimization.

[0120] The dynamic feedback and adjustment process is as follows. For details not described in detail, please refer to the corresponding method implementation examples above: First, based on the concentration map The system continuously monitors AMC concentration changes in various areas of the cleanroom through real-time updates. The core of the dynamic feedback mechanism is to detect new concentration anomalies through cyclical feedback and promptly trigger corresponding optimization strategies (local or global optimization).

[0121] Secondly, concentration anomaly detection was performed. Concentration data for each area was analyzed. Real-time monitoring will be conducted, and if the concentration value at any location exceeds the set threshold... This triggers local optimization, rapidly adjusting the FFU wind speed in and around the pollution source.

[0122] Triggering condition formula:

[0123] During the local optimization phase, the wind speed of the FFUs (Fan Filter Units) in and around the pollution source is dynamically adjusted to reduce pollution diffusion. After local optimization, the wind speed is updated in real time.

[0124] in, This represents the minimum wind speed of the FFU. This represents the maximum value of the FFU wind speed; This represents the maximum possible value of AMC concentration. The preset threshold; Concentration for each region.

[0125] Then, when the concentration at the pollution source returns to normal levels (i.e. After the local adjustments are completed, the system enters the recovery phase. The system then enters the global optimization phase to balance the impact of the local adjustments on the overall cleanroom airflow. During the global optimization phase, the airflow velocity of all FFUs is redistributed based on the results of particle swarm optimization. This ensures that all FFUs operate at optimal wind speeds, guaranteeing overall airflow stability in the cleanroom.

[0126] To avoid new concentration fluctuations caused by sudden changes in wind speed, the system gradually restores the FFU wind speed:

[0127] in, This refers to the current wind speed; Wind speed values ​​optimized globally; This is the recovery rate coefficient, with a value ranging from [0,1]. Larger values... This indicates a slower recovery speed, making it suitable for scenarios sensitive to airflow.

[0128] Finally, the system updates the concentration map at fixed time intervals (e.g., 1 second). This ensures that FFU wind speed adjustments are always based on the latest data.

[0129] Updated formula:

[0130] in, For sensor to location The weighting factor is used. Real-time concentration data is stored in a database for subsequent analysis of cleanroom contamination patterns. Historical data analysis is used to predict potential contamination source locations or high-risk areas, and to optimize sensor and FFU layout. Simultaneously, a real-time updated concentration map is generated. This allows for a direct view of the latest AMC concentration distribution across all areas of the cleanroom.

[0131] FFU wind speed allocation updated after dynamic feedback :

[0132] The wind speed distribution output from the dynamic feedback is directly applied to FFU control, providing input for the next round of optimization.

[0133] During the above dynamic optimization process, even if no concentration anomalies occur in the cleanroom, the global optimization will continue according to the preset cycle. This is done to ensure the long-term stability of the cleanroom's operation.

[0134] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0135] Figure 3 A schematic diagram of a cleanroom contaminant concentration control device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 3 As shown, the cleanroom contaminant concentration control device 3 includes: The acquisition module 301 is used to acquire the real-time AMC concentration of each area in the cleanroom based on the cleanroom space area division results; The wind speed correction module 302 is used to adjust the wind speed correction value of each FFU in the target area based on the distance between the target area and the other areas when the real-time AMC concentration in the target area is greater than or equal to the concentration threshold. The closer the distance to the target area, the larger the corresponding wind speed correction value. The wind speed optimization module 303 is used to obtain the current AMC concentration value of each area when the AMC concentration in the target area is less than the concentration threshold, and determine the optimal solution of FFU wind speed based on the current AMC concentration value of each area, cleanroom FFU layout information and PSO. The adjustment module 304 is used to adjust the wind speed of each FFU according to the optimal solution of FFU wind speed.

[0136] In this embodiment, the cleanroom contaminant concentration control method monitors the AMC concentration in each area in real time. When the concentration in a target area exceeds the limit, the FFU wind speed correction value is adjusted based on the distance from that area, with a larger correction value for closer areas. This method can specifically strengthen airflow control near the contaminant source and quickly suppress contaminant diffusion. Once the concentration drops below the threshold, the optimal wind speed is determined by combining the current concentration, FFU layout, and PSO algorithm. This ensures the stability of the overall cleanroom concentration and achieves global wind speed optimization through intelligent algorithms, thus ensuring both rapid response to contamination risks and high system efficiency.

[0137] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 40 and a memory 41. The memory 41 stores a computer program 42. When the processor 40 executes the computer program 42, it implements the steps in the various method embodiments described above. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module / unit in the various device embodiments described above.

[0138] For example, computer program 42 may be divided into one or more modules / units, which are stored in memory 41 and executed by processor 40 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0139] Electronic device 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0140] The processor 40 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0141] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store the computer program 42 and other programs and data required by the electronic device 4. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0142] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0143] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0144] This invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0145] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0146] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0147] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for controlling the concentration of contaminants in a cleanroom, characterized in that, include: Based on the cleanroom space zoning results, the real-time concentration of gaseous molecular pollutants (AMC) in each area of ​​the cleanroom is obtained; When the real-time AMC concentration in the target area is greater than or equal to the concentration threshold, the wind speed correction value of the fan filter unit (FFU) in each area is adjusted based on the distance between the target area and the other areas; wherein, the closer the distance to the target area, the larger the corresponding wind speed correction value. When the AMC concentration in the target area is less than the concentration threshold, the current AMC concentration value of each area is obtained, and the optimal solution for FFU wind speed is determined based on the current AMC concentration value of each area, the cleanroom FFU layout information, and the particle swarm optimization algorithm (PSO). Adjust the wind speed of each FFU according to the optimal solution of FFU wind speed.

2. The method for controlling the concentration of contaminants in a cleanroom according to claim 1, characterized in that, The process of determining the optimal FFU airflow velocity based on the current AMC concentration value of each area, the cleanroom FFU layout information, and PSO includes: Determine the number of FFUs based on the cleanroom FFU layout information; Initialize the particle swarm size, particle position, and particle velocity using the number of FFUs, the current wind speed of each FFU, and wind speeds within a set wind speed range. In each iteration, the fitness function value of the particle corresponding to each FFU is calculated, and the individual optimal position is updated according to the wind speed corresponding to the optimal fitness of each FFU. The global optimal position is updated according to the wind speed corresponding to the optimal fitness of all FFUs. Based on the individual optimal position and the global optimal position, the velocity and position of the particles corresponding to each FFU are updated. When the convergence condition is met, the corresponding global optimal solution is used as the optimal solution for the FFU wind speed.

3. The method for controlling the concentration of contaminants in a cleanroom according to claim 2, characterized in that, The convergence conditions include: In multiple consecutive iterations, the change in the fitness function value corresponding to the global optimal position is less than a set threshold, or the number of iterations reaches the preset maximum number.

4. The method for controlling the concentration of contaminants in a cleanroom according to claim 1, characterized in that, The acquisition of real-time AMC concentrations in various areas of the cleanroom includes: AMC concentration monitoring data is collected from all sensors distributed throughout the cleanroom space at a set period; wherein, the AMC concentration monitoring data includes sensor number and AMC concentration detection value; The coordinates of the sensor are determined based on the sensor number, and a data matrix is ​​constructed based on the sensor coordinates and the corresponding AMC concentration detection value. A concentration map is drawn based on the data matrix, and the average AMC concentration of all grid points in each region is determined as the AMC concentration of each region based on the concentration map.

5. The method for controlling the concentration of contaminants in a cleanroom according to claim 4, characterized in that, Before determining the sensor's coordinates based on the sensor number, the method further includes: The AMC concentration detection values ​​of each sensor are preprocessed; the preprocessing includes outlier detection, missing value imputation and noise reduction smoothing.

6. The method for controlling the concentration of contaminants in a cleanroom according to claim 4, characterized in that, The step of drawing a concentration map based on the data matrix includes: The target grid points with missing AMC concentration values ​​are determined by comparing the coordinates of each grid point with those of the sensor. Calculate the AMC concentration value of the target grid point based on the data matrix and interpolation algorithm; A concentration map is drawn based on the AMC concentration values ​​and grid coordinates of each grid point.

7. The method for controlling the concentration of contaminants in a cleanroom according to claim 6, characterized in that, The AMC concentration values ​​of the target grid points are calculated based on the data matrix and interpolation algorithm. include: The AMC concentration value of the target grid point is determined using the inverse distance weighting method, as shown in the following formula: in, For the first AMC concentration values ​​from each sensor; For grid points To the sensor Euclidean distance: ; This is the distance-weighted index.

8. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images